← Back to community benchmarks
Qwen3.5-4B
Performance
4k
tokens
340.8
PP tok/s
34.4
TG tok/s
12017
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 349.0 | 36.1 | 3.9 GB | view |
| 4k | 340.8 | 34.4 | 4.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 36.1 | 1.00× |
| 2× | 66.7 | 1.85× |
| 4× | 67.8 | 1.88× |